Does Dependency Locality Predict Non-canonical Word Order in Hindi?

• URL: http://arxiv.org/abs/2405.07730v1
• Date: Mon, 13 May 2024 13:24:17 GMT
• Title: Does Dependency Locality Predict Non-canonical Word Order in Hindi?
• Authors: Sidharth Ranjan, Marten van Schijndel,
• Abstract summary: dependency length minimization is a significant predictor of non-canonical (OSV) syntactic choices. discourse predictability emerges as the primary determinant of constituent-order preferences. This work sheds light on the role of expectation adaptation in word-ordering decisions.
• Score: 5.540151072128081
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Previous work has shown that isolated non-canonical sentences with Object-before-Subject (OSV) order are initially harder to process than their canonical counterparts with Subject-before-Object (SOV) order. Although this difficulty diminishes with appropriate discourse context, the underlying cognitive factors responsible for alleviating processing challenges in OSV sentences remain a question. In this work, we test the hypothesis that dependency length minimization is a significant predictor of non-canonical (OSV) syntactic choices, especially when controlling for information status such as givenness and surprisal measures. We extract sentences from the Hindi-Urdu Treebank corpus (HUTB) that contain clearly-defined subjects and objects, systematically permute the preverbal constituents of those sentences, and deploy a classifier to distinguish between original corpus sentences and artificially generated alternatives. The classifier leverages various discourse-based and cognitive features, including dependency length, surprisal, and information status, to inform its predictions. Our results suggest that, although there exists a preference for minimizing dependency length in non-canonical corpus sentences amidst the generated variants, this factor does not significantly contribute in identifying corpus sentences above and beyond surprisal and givenness measures. Notably, discourse predictability emerges as the primary determinant of constituent-order preferences. These findings are further supported by human evaluations involving 44 native Hindi speakers. Overall, this work sheds light on the role of expectation adaptation in word-ordering decisions. We conclude by situating our results within the theories of discourse production and information locality.

Related papers

• Surprise! Uniform Information Density Isn't the Whole Story: Predicting Surprisal Contours in Long-form Discourse [54.08750245737734]
  We propose that speakers modulate information rate based on location within a hierarchically-structured model of discourse. We find that hierarchical predictors are significant predictors of a discourse's information contour and that deeply nested hierarchical predictors are more predictive than shallow ones.
  arXiv  Detail & Related papers  (2024-10-21T14:42:37Z)
• To Drop or Not to Drop? Predicting Argument Ellipsis Judgments: A Case Study in Japanese [26.659122101710068]
  We study whether and why a particular argument should be omitted across over 2,000 data points in the balanced corpus of Japanese. The data indicate that native speakers overall share common criteria for such judgments. The gap between the systems' prediction and human judgments in specific linguistic aspects is revealed.
  arXiv  Detail & Related papers  (2024-04-17T12:26:52Z)
• Natural Language Decompositions of Implicit Content Enable Better Text Representations [56.85319224208865]
  We introduce a method for the analysis of text that takes implicitly communicated content explicitly into account. We use a large language model to produce sets of propositions that are inferentially related to the text that has been observed. Our results suggest that modeling the meanings behind observed language, rather than the literal text alone, is a valuable direction for NLP.
  arXiv  Detail & Related papers  (2023-05-23T23:45:20Z)
• A bounded rationality account of dependency length minimization in Hindi [0.0]
  The principle of DEPENDENCY LENGTH MINIMIZATION is thought to shape the structure of human languages for effective communication. Preverbally, the placement of long-before-short constituents and postverbally, short-before-long constituents are known to minimize overall dependency length of a sentence. In this study, we test the hypothesis that placing only the shortest preverbal constituent next to the main-verb explains word order preferences in Hindi.
  arXiv  Detail & Related papers  (2023-04-22T13:53:50Z)
• Towards preserving word order importance through Forced Invalidation [80.33036864442182]
  We show that pre-trained language models are insensitive to word order. We propose Forced Invalidation to help preserve the importance of word order. Our experiments demonstrate that Forced Invalidation significantly improves the sensitivity of the models to word order.
  arXiv  Detail & Related papers  (2023-04-11T13:42:10Z)
• Discourse Context Predictability Effects in Hindi Word Order [14.88833412862455]
  We investigate how the words and syntactic structures in a sentence influence the word order of the following sentences. We use a number of discourse-based features and cognitive features to make its predictions, including dependency length, surprisal, and information status. We find that information status and LSTM-based discourse predictability influence word order choices, especially for non-canonical object-fronted orders.
  arXiv  Detail & Related papers  (2022-10-25T11:53:01Z)
• Contextualized Semantic Distance between Highly Overlapped Texts [85.1541170468617]
  Overlapping frequently occurs in paired texts in natural language processing tasks like text editing and semantic similarity evaluation. This paper aims to address the issue with a mask-and-predict strategy. We take the words in the longest common sequence as neighboring words and use masked language modeling (MLM) to predict the distributions on their positions. Experiments on Semantic Textual Similarity show NDD to be more sensitive to various semantic differences, especially on highly overlapped paired texts.
  arXiv  Detail & Related papers  (2021-10-04T03:59:15Z)
• Deep Subjecthood: Higher-Order Grammatical Features in Multilingual BERT [7.057643880514415]
  We investigate how Multilingual BERT (mBERT) encodes grammar by examining how the high-order grammatical feature of morphosyntactic alignment is manifested across the embedding spaces of different languages.
  arXiv  Detail & Related papers  (2021-01-26T19:21:59Z)
• Infusing Finetuning with Semantic Dependencies [62.37697048781823]
  We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
  arXiv  Detail & Related papers  (2020-12-10T01:27:24Z)
• On the Sentence Embeddings from Pre-trained Language Models [78.45172445684126]
  In this paper, we argue that the semantic information in the BERT embeddings is not fully exploited. We find that BERT always induces a non-smooth anisotropic semantic space of sentences, which harms its performance of semantic similarity. We propose to transform the anisotropic sentence embedding distribution to a smooth and isotropic Gaussian distribution through normalizing flows that are learned with an unsupervised objective.
  arXiv  Detail & Related papers  (2020-11-02T13:14:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.